INDEX

Explanations

words related to starting and ending events or actions

oai_token-act-pair · gpt-3.5-turbo

references to start and end processes or activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phia

-0.78

 pens

-0.72

é¾įå

-0.70

pell

-0.69

riend

-0.68

avis

-0.67

ynt

-0.66

onyms

-0.64

enhagen

-0.64

 cats

-0.64

POSITIVE LOGITS

 countdown

0.67

 Sequence

0.67

endment

0.67

requisites

0.64

 sequence

0.63

 Destination

0.61

enium

0.61

 Makoto

0.61

adder

0.60

 anew

0.58

Activations Density 0.397%

words related to starting and ending events or actions

references to start and end processes or activities

No Comments

No Known Activations